Rchr
J-GLOBAL ID:202401006375988490   Update date: Nov. 30, 2024

Yoshida Naoto

ヨシダ ナオト | Yoshida Naoto
Affiliation and department:
Job title: Project-Specific Researcher
Other affiliations (1):
Homepage URL  (1): https://sites.google.com/view/movingsloth
Research field  (2): Intelligent robotics ,  Neuroscience - general
Research keywords  (8): Human-Robot Interaction ,  Homeostasis ,  Neural Networks ,  Deep Reinforcement Learning ,  Robotics ,  Embodied Intelligence ,  Computational Neuroscience ,  Reinforcement Learning
Research theme for competitive and other funds  (2):
  • 2024 - 2026 深層恒常性強化学習におけるメタ強化学習性の創発
  • 2023 - 2024 Development of the adaptive agent for homeostasis and analysis of its cognitive development
Papers (13):
  • Naoto Yoshida, Etsushi Arikawa, Hoshinori Kanazawa, Yasuo Kuniyoshi. Modeling long-term nutritional behaviors using deep homeostatic reinforcement learning. PNAS Nexus. 2024
  • Naoto Yoshida, Tatsuya Daikoku, Yukie Nagai, Yasuo Kuniyoshi. Emergence of integrated behaviors through direct optimization for homeostasis. Neural Networks. 2024. 177. 106379-106379
  • Naoto Yoshida, Hoshinori Kanazawa, Yasuo Kuniyoshi. Synthesising integrated robot behaviour through reinforcement learning for homeostasis. bioRxiv. 2024
  • 吉田尚人. 恒常性に基づく自律エージェントの行動創発に関する構成論的研究. 東京大学大学院大学情報理工学系研究科博士論文. 2024
  • Naoto Yoshida, Hoshinori Kanazawa, Yasuo Kuniyoshi. Homeostatic Reinforcement Learning through Soft Behavior Switching with Internal Body State. 2023 International Joint Conference on Neural Networks (IJCNN). 2023
more...
MISC (14):
  • Kazuya Horibe, Naoto Yoshida. Emergence of Implicit World Models from Mortal Agents. 2024
  • Kingson Man, Ignacio Cea, Naoto Yoshida. Emergence of prosocial behavior in homeostatic reinforcement learning with vulnerable agents. The 27th annual meeting of the Association for the Scientific Study of Consciousness. 2024
  • Naoto Yoshida, Tadahiro Taniguchi. Toward collective predictive coding for emergent communication in embodied agents. Pre-ASSC Satellite Workshop: Structural approaches to consciousness: Qualia Structure and Integrated Information Theory. 2024
  • Yoshida, N, Kuniyoshi, Y. Empirical evidence for the emergence of non-trivial behavior from optimization for homeostasis. The 1st International Workshop on Cognitive Neurorobotics. 2024
  • Naoto Yoshida. Exploring Embodied Intelligence. Neural Computation Workshop 2024. 2024
more...
Lectures and oral presentations  (6):
  • 深層恒常性強化学習による恒常性に対して非自明な行動の創発
    (2024年度人工知能学会全国大会(第38回) 2024)
  • 深層恒常性強化学習と内受容感覚に基づく方策選択機構
    (2023年度人工知能学会全国大会(第37回) 2023)
  • コンパニオンロボッ トにおける愛着形成を実現させるアニメーション表現を取り入れた行動の設計
    (第 38 回日本ロ ボット学会学術講演会 2020)
  • 愛着シナリオ分析に よるコンパニオンロボットのデバイス要件と実システムの提案
    (第 38 回日本ロボット学会学術 講演会 2020)
  • エネルギべースドモデルを用いた強化学習のための多層パーセプトロン構造
    (人工知能学会全国大会論文集 第 29 回全国大会 2016)
more...
Education (3):
  • 2020 - 2024 The University of Tokyo Graduate School of Information Science and Technology Doctoral Program Mechano-Informatics
  • 2010 - 2012 Nara Institute of Science and Technology Information Science
  • 2006 - 2010 Tohoku University Faculty of Engineering Department of Mechanical and Aerospace Engineering
Professional career (1):
  • Doctor of Philosophy in the field of Information Science and Technology (The University of Tokyo)
Work history (4):
  • 2024/04 - 現在 Kyoto University Graduate School of Informatics Project-specific Researcher
  • 2022/04 - 2024/03 Japan Society for the Promotion of Science JSPS Research Fellow
  • 2016/10 - 2020/05 GROOVE X, Inc. Software Engineer, Behavior Design
  • 2011/03 - 2013/09 Okinawa Institute of Science and Technology Graduate University Neural Computation Unit Visiting Fellow
Awards (3):
  • 2019/11 - Whole Brain Architecture Initiative WBAI Incentive Award Homeostatic agent for general environment
  • 2013/08 - IEEE, The third joint IEEE international conference on development and learning and on epigenetic robotics Student Travel Award Reinforcement learning with state-dependent discount factor
  • 2011/02 - Okinawa Institute of Science and Technology OIST Essay Contest A multidisciplinary approach to solving complicated problems in science and technology today
Association Membership(s) (1):
The Japanese Society for Artificial Intelligence
※ Researcher’s information displayed in J-GLOBAL is based on the information registered in researchmap. For details, see here.

Return to Previous Page